view post Post 16 QwQ can see π₯Qwen team released QvQ, a large vision LM with reasoning π±it outperforms proprietary VLMs on several benchmarks, comes with open weights and a demo! Check them out β¬οΈDemo Qwen/QVQ-72B-previewModel Qwen/QVQ-72B-PreviewRead more https://qwenlm.github.io/blog/qvq-72b-preview/Congratulations @JustinLin610 and team! See translation
view post Post 2244 Aya by Cohere For AI can now see! πC4AI community has built Maya 8B, a new open-source multilingual VLM built on SigLIP and Aya 8B π± works on 8 languages! π£οΈ The authors extend Llava dataset using Aya's translation capabilities with 558k examples! ry it here kkr5155/maya_demoDataset maya-multimodal/pretrainModel maya-multimodal/maya π kudos @nahidalam and team See translation
Dec 6 Releases π meta-llama/Llama-3.3-70B-Instruct Text Generation β’ Updated 3 days ago β’ 277k β’ β’ 1.28k Qwen/Qwen2-VL-72B Image-Text-to-Text β’ Updated 19 days ago β’ 732 β’ 64 google/paligemma2-3b-pt-224 Image-Text-to-Text β’ Updated 19 days ago β’ 25.7k β’ 112 tencent/HunyuanVideo Text-to-Video β’ Updated 7 days ago β’ 6.74k β’ 1.25k
Nov 29 Releases π²π² HuggingFaceTB/SmolVLM-Instruct Image-Text-to-Text β’ Updated 22 days ago β’ 77.2k β’ 296 Qwen/QwQ-32B-Preview Text Generation β’ Updated 25 days ago β’ 122k β’ β’ 1.4k nvidia/Hymba-1.5B-Base Text Generation β’ Updated 10 days ago β’ 7.68k β’ 128 vidore/colsmolvlm-alpha Updated 21 days ago β’ 2.12k β’ 46